Edisonhimself

作者大佬您好！ 我想先通过“model = GPT2LMHeadModel.from_pretrained(args.pretrained_model)”加载预训练模型然后在它的基础上进行微调 我想问您的代码中这样进行微调的方式是在加载的模型的参数的基础上进行全参数微调吗？

What does the parameter "data" printed during training mean

1

**What does the parameter "data" printed during training mean** 

**The order of connection between word vectors and image vectors in prompt** Thank you for your work. I have a few questions regarding **the concatenation order of the image vectors...